Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic

2025. 11. 09.
OSINT 협회
OSINT 정보
Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic They call it "Whisper Leak" side-channel attack. And in tests, models like OpenAI and Mistral gave away topics with 98% accuracy.
Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic They call it "Whisper Leak" side-channel attack. And in tests, models like OpenAI and Mistral gave away topics with 98% accuracy.
게시일: 2025. 11. 09.
출처: OSINT 협회 Facebook
원본 Facebook 게시물 보기 →
이전

Malicious NuGet packages drop disruptive 'time bombs'

다음

Google Warns of New 'PROMPTFLUX' Malware Using Gemini API to Rewrite Its Own Source Code